No Annotations for Object Detection in Art through Stable Diffusion

TL;DR

NADA introduces a novel pipeline leveraging diffusion models for zero-shot and weakly-supervised object detection in art images, eliminating the need for manual annotations and fine-tuning.

Contribution

It is the first approach to enable zero-shot object detection in art using diffusion models without requiring annotations or fine-tuning.

Findings

Outperforms prior weakly-supervised methods on ArtDL 2.0 and IconArt datasets.

First work to achieve zero-shot object detection in art images.

Supports both weakly-supervised and zero-shot scenarios without fine-tuning.

Abstract

Object detection in art is a valuable tool for the digital humanities, as it allows for faster identification of objects in artistic and historical images compared to humans. However, annotating such images poses significant challenges due to the need for specialized domain expertise. We present NADA (no annotations for detection in art), a pipeline that leverages diffusion models' art-related knowledge for object detection in paintings without the need for full bounding box supervision. Our method, which supports both weakly-supervised and zero-shot scenarios and does not require any fine-tuning of its pretrained components, consists of a class proposer based on large vision-language models and a class-conditioned detector based on Stable Diffusion. NADA is evaluated on two artwork datasets, ArtDL 2.0 and IconArt, outperforming prior work in weakly-supervised detection, while being the first work for zero-shot object detection in art. Code is available at https://github.com/patrick-john-ramos/nada